statsample 0.11.2 → 0.12.0

data/lib/statsample/factor/pca.rb

@@ -39,7 +39,7 @@ module Factor
     include GetText
     bindtextdomain("statsample")
     
-    def initialize(matrix ,opts=Hash.new)
+    def initialize(matrix, opts=Hash.new)
 	@use_gsl=nil
       @name=_("Principal Component Analysis")
       @matrix=matrix

data/lib/statsample/graph/svgscatterplot.rb

@@ -1,3 +1,4 @@
+require 'tempfile'
 module Statsample
   module Graph
     class SvgScatterplot < SVG::Graph::Plot # :nodoc:
@@ -7,6 +8,14 @@ module Statsample
           @ds=ds
           set_x(@ds.fields[0])
       end
+      def report_building_html(g)
+        self.parse()
+        tf=Tempfile.new(['image','.svg'])
+        tf.write self.burn
+        tf.close
+        image=ReportBuilder::Image.new(tf.path)
+        g.parse_element(image)
+      end
       def set_defaults
           super
           init_with(
@@ -27,7 +36,7 @@ module Statsample
         }
         data.each{|y,d|
           add_data({
-                  :data=>d, :title=>@ds.vector_label(y)
+              :data=>d, :title=>@ds[y].name
           })
         }
       end

data/lib/statsample/reliability.rb

@@ -21,13 +21,44 @@ module Statsample
         }.to_dataset
         cronbach_alpha(ds)
       end
+      def cronbach_alpha_from_n_s2_cov(n,s2,cov)
+        (n.quo(n-1)) * (1-(s2.quo(s2+(n-1)*cov)))
+      end
+      # Returns n necessary to obtain specific alpha
+      # given variance and covariance mean of items
+      def n_for_desired_alpha(alpha,s2,cov)
+        # Start with a regular test : 50 items
+        min=2
+        max=1000
+        n=50
+        prev_n=0
+        epsilon=0.0001
+        dif=1000
+        c_a=cronbach_alpha_from_n_s2_cov(n,s2,cov)
+        dif=c_a - alpha
+        while(dif.abs>epsilon and n!=prev_n)
+          prev_n=n
+          if dif<0
+            min=n
+            n=(n+(max-min).quo(2)).to_i
+          else
+            max=n
+            n=(n-(max-min).quo(2)).to_i
+          end
+          c_a=cronbach_alpha_from_n_s2_cov(n,s2,cov)
+          dif=c_a - alpha
+          #puts "#{n} , #{c_a}"
+          
+        end
+        n
+      end
       # First derivative for alfa
       # Parameters
       # <tt>n</tt>: Number of items
       # <tt>sx</tt>: mean of variances 
       # <tt>sxy</tt>: mean of covariances
       
-      def alfa_first_derivative(n,sx,sxy)
+      def alpha_first_derivative(n,sx,sxy)
         (sxy*(sx-sxy)).quo(((sxy*(n-1))+sx)**2)
       end
       # Second derivative for alfa
@@ -75,193 +106,9 @@ module Statsample
           out[value]=count_value.quo(n)
         end
         out
-      end
-    end
-    class ItemAnalysis
-      attr_reader :mean, :sd,:valid_n, :alpha , :alpha_standarized, :variances_mean, :covariances_mean
-      attr_accessor :name
-      def initialize(ds,opts=Hash.new)
-        @ds=ds.dup_only_valid
-        @k=@ds.fields.size
-        @total=@ds.vector_sum
-        @item_mean=@ds.vector_mean.mean
-        @mean=@total.mean
-        @median=@total.median
-        @skew=@total.skew
-        @kurtosis=@total.kurtosis
-        @sd = @total.sd
-        @variance=@total.variance
-        @valid_n = @total.size
-        opts_default={:name=>"Reliability Analisis"}
-        @opts=opts_default.merge(opts)
-        @name=@opts[:name]
-        # Mean for covariances and variances
-        @variances=@ds.fields.map {|f| @ds[f].variance}.to_scale
-        @variances_mean=@variances.mean
-        @covariances_mean=(@variance-@variances.sum).quo(@k**2-@k)
-        begin
-          @alpha = Statsample::Reliability.cronbach_alpha(ds)
-          @alpha_standarized = Statsample::Reliability.cronbach_alpha_standarized(ds)
-        rescue => e
-          raise DatasetException.new(@ds,e), "Error calculating alpha"
-        end
-      end
-      # Returns a hash with structure
-      def item_characteristic_curve
-        i=0
-        out={}
-        total={}
-        @ds.each do |row|
-          tot=@total[i]
-          @ds.fields.each do |f|
-            out[f]||= {}
-            total[f]||={}
-            out[f][tot]||= 0
-            total[f][tot]||=0
-            out[f][tot]+= row[f]
-            total[f][tot]+=1
-          end
-          i+=1
-        end
-        total.each do |f,var|
-          var.each do |tot,v|
-            out[f][tot]=out[f][tot].to_f / total[f][tot]
-          end
-        end
-        out
-      end
-      def gnuplot_item_characteristic_curve(directory, base="crd",options={})
-        require 'gnuplot'
-
-        crd=item_characteristic_curve
-        @ds.fields.each  do |f|
-          x=[]
-          y=[]
-          Gnuplot.open do |gp|
-            Gnuplot::Plot.new( gp ) do |plot|
-              crd[f].sort.each do |tot,prop|
-                x.push(tot)
-                y.push((prop*100).to_i.to_f/100)
-              end
-              plot.data << Gnuplot::DataSet.new( [x, y] ) do |ds|
-                ds.with = "linespoints"
-                ds.notitle
-              end
-
-            end
-          end
-        end
-      end
-      def svggraph_item_characteristic_curve(directory, base="icc",options={})
-        require 'statsample/graph/svggraph'
-        crd=ItemCharacteristicCurve.new(@ds)
-        @ds.fields.each do |f|
-          factors=@ds[f].factors.sort
-          options={
-            :height=>500,
-            :width=>800,
-            :key=>true
-          }.update(options)
-          graph = ::SVG::Graph::Plot.new(options)
-          factors.each do |factor|
-            factor=factor.to_s
-            dataset=[]
-            crd.curve_field(f, factor).each do |tot,prop|
-              dataset.push(tot)
-              dataset.push((prop*100).to_i.to_f/100)
-            end
-            graph.add_data({
-              :title=>"#{factor}",
-              :data=>dataset
-            })
-          end
-          File.open(directory+"/"+base+"_#{f}.svg","w") {|fp|
-            fp.puts(graph.burn())
-          }
-        end
-      end
-      def item_total_correlation
-        @ds.fields.inject({}) do |a,v|
-          vector=@ds[v].dup
-          ds2=@ds.dup
-          ds2.delete_vector(v)
-          total=ds2.vector_sum
-          a[v]=Statsample::Bivariate.pearson(vector,total)
-          a
-        end
-      end
-      def item_statistics
-        @ds.fields.inject({}) do |a,v|
-          a[v]={:mean=>@ds[v].mean,:sds=>@ds[v].sds}
-          a
-        end
-      end
-      # Returns a dataset with cases ordered by score
-      # and variables ordered by difficulty
-
-      def item_difficulty_analysis
-        dif={}
-        @ds.fields.each{|f| dif[f]=@ds[f].mean }
-        dif_sort=dif.sort{|a,b| -(a[1]<=>b[1])}
-        scores_sort={}
-        scores=@ds.vector_mean
-        scores.each_index{|i| scores_sort[i]=scores[i] }
-        scores_sort=scores_sort.sort{|a,b| a[1]<=>b[1]}
-        ds_new=Statsample::Dataset.new(['case','score'] + dif_sort.collect{|a,b| a})
-        scores_sort.each do |i,score|
-          row=[i, score]
-          case_row=@ds.case_as_hash(i)
-          dif_sort.each{|variable,dif_value| row.push(case_row[variable]) }
-          ds_new.add_case_array(row)
-        end
-        ds_new.update_valid_data
-        ds_new
-      end
-      def stats_if_deleted
-        @ds.fields.inject({}) do |a,v|
-          ds2=@ds.dup
-          ds2.delete_vector(v)
-          total=ds2.vector_sum
-          a[v]={}
-          a[v][:mean]=total.mean
-          a[v][:sds]=total.sds
-          a[v][:variance_sample]=total.variance_sample
-          a[v][:alpha]=Statsample::Reliability.cronbach_alpha(ds2)
-          a
-        end
-      end
-      def summary
-        ReportBuilder.new(:no_title=>true).add(self).to_text
-      end
-      def report_building(builder)
-        builder.section(:name=>@name) do |s|
-          s.table(:name=>"Summary") do |t|
-            t.row ["Items", @ds.fields.size]
-            t.row ["Total Mean", @mean]
-            t.row ["Total S.D.", @sd]
-            t.row ["Total Variance", @variance]
-            t.row ["Item Mean", @item_mean]
-            t.row ["Median", @median]
-            t.row ["Skewness", "%0.4f" % @skew]
-            t.row ["Kurtosis", "%0.4f" % @kurtosis]
-            t.row ["Valid n", @valid_n]
-            t.row ["Cronbach's alpha", "%0.4f" % @alpha]
-            t.row ["Standarized Cronbach's alpha", "%0.4f" % @alpha_standarized]
-            t.row ["Variances mean",  "%g" % @variances_mean]
-            t.row ["Covariances mean" , "%g" % @covariances_mean]
-          end
-          
-          itc=item_total_correlation
-          sid=stats_if_deleted
-          is=item_statistics
-
-          s.table(:name=>"Items report", :header=>["item","mean","sd", "mean if deleted", "var if deleted", "sd if deleted"," item-total correl.", "alpha if deleted"]) do |t|
-            @ds.fields.each do |f|
-              t.row(["#{@ds[f].name}(#{f})", sprintf("%0.5f",is[f][:mean]), sprintf("%0.5f",is[f][:sds]), sprintf("%0.5f",sid[f][:mean]), sprintf("%0.5f",sid[f][:variance_sample]), sprintf("%0.5f",sid[f][:sds]),  sprintf("%0.5f",itc[f]), sprintf("%0.5f",sid[f][:alpha])])
-            end
-          end
-          end
-      end
-    end
-  end
-end
+      end # def
+    end # self
+   end # Reliability
+ end # Statsample
+require 'statsample/reliability/scaleanalysis.rb'
+require 'statsample/reliability/multiscaleanalysis.rb'

data/lib/statsample/reliability/multiscaleanalysis.rb

@@ -0,0 +1,87 @@
+module Statsample
+  module Reliability
+    # DSL for analysis of multiple scales analysis. Analoge of Scale Reliability analysis on SPSS.
+    # Returns several statistics for complete scale and each item
+    # == Usage
+    #  @x1=[1,1,1,1,2,2,2,2,3,3,3,30].to_vector(:scale)
+    #  @x2=[1,1,1,2,2,3,3,3,3,4,4,50].to_vector(:scale)
+    #  @x3=[2,2,1,1,1,2,2,2,3,4,5,40].to_vector(:scale)
+    #  @x4=[1,2,3,4,4,4,4,3,4,4,5,30].to_vector(:scale)
+    #  ds={'x1'=>@x1,'x2'=>@x2,'x3'=>@x3,'x4'=>@x4}.to_dataset
+    #  msa=Statsample::Reliability::MultiScaleAnalysis.new(:name=>"Scales") do |m|
+    #    m.scale :s1, "Section 1", ds.clone(%w{x1 x2})
+    #    m.scale :s2, "Section 2", ds.clone(%w{x3 x4})
+    #    m.correlation_matrix
+    #    m.factor_analysis
+    #  end
+    #  puts msa.summary
+    class MultiScaleAnalysis
+      include Statsample::Summarizable
+      attr_reader :scales
+      attr_accessor :name
+      attr_accessor :summary_correlation_matrix
+      attr_accessor :summary_pca
+      attr_accessor :pca_options
+      def initialize(opts=Hash.new, &block)
+        @scales=Hash.new
+        opts_default={  :name=>_("Multiple Scale analysis"),
+                        :summary_correlation_matrix=>false,
+                        :summary_pca=>false,
+                        :pca_options=>Hash.new}
+        @opts=opts_default.merge(opts)
+        @opts.each{|k,v|
+          self.send("#{k}=",v) if self.respond_to? k
+        }
+
+        if block
+          block.arity<1 ? instance_eval(&block) : block.call(self)
+        end
+      end
+      def scale(code,ds=nil, opts=nil)
+        if ds.nil?
+          @scales[code]
+        else
+          opts={:name=>_("Scale %s") % code} if opts.nil?
+          @scales[code]=ScaleAnalysis.new(ds, opts)
+        end
+      end
+      def delete_scale(code)
+        @scales.delete code
+      end
+      def pca(opts=Hash.new)
+        Statsample::Factor::PCA.new(correlation_matrix,opts)
+      end
+      def factor_analysis(opts=nil)
+        opts||=pca_options
+        Statsample::Factor::FactorAnalysis.new(correlation_matrix,opts)
+      end
+      
+      def correlation_matrix
+        vectors=Hash.new
+        @scales.each_pair do |code,scale|
+          vectors[code.to_s]=scale.ds.vector_sum
+        end
+        Statsample::Bivariate.correlation_matrix(vectors.to_dataset)
+      end
+      def report_building(b)
+        b.section(:name=>name) do |s|
+          s.section(:name=>_("Reliability analysis of scales")) do |s2|
+            @scales.each_pair do |k,scale|
+              s2.parse_element(scale)
+            end
+          end
+          if summary_correlation_matrix
+            s.section(:name=>_("Correlation matrix for %s") % name) do |s2|
+              s2.parse_element(correlation_matrix)
+            end
+          end
+          if summary_pca
+            s.section(:name=>_("PCA for %s") % name) do |s2|
+              s2.parse_element(pca)
+            end
+          end
+        end
+      end
+    end
+  end
+end

data/lib/statsample/reliability/scaleanalysis.rb

@@ -0,0 +1,204 @@
+module Statsample
+  module Reliability
+    # Analysis of a Scale. Analoge of Scale Reliability analysis on SPSS.
+    # Returns several statistics for complete scale and each item
+    # == Usage
+    #  @x1=[1,1,1,1,2,2,2,2,3,3,3,30].to_vector(:scale)
+    #  @x2=[1,1,1,2,2,3,3,3,3,4,4,50].to_vector(:scale)
+    #  @x3=[2,2,1,1,1,2,2,2,3,4,5,40].to_vector(:scale)
+    #  @x4=[1,2,3,4,4,4,4,3,4,4,5,30].to_vector(:scale)
+    #  ds={'x1'=>@x1,'x2'=>@x2,'x3'=>@x3,'x4'=>@x4}.to_dataset
+    #  ia=Statsample::Reliability::ScaleAnalysis.new(ds)
+    #  puts ia.summary
+    class ScaleAnalysis
+      include Summarizable
+      attr_reader :ds,:mean, :sd,:valid_n, :alpha , :alpha_standarized, :variances_mean, :covariances_mean
+      attr_accessor :name
+      def initialize(ds, opts=Hash.new)
+        @ds=ds.dup_only_valid
+        @k=@ds.fields.size
+        @total=@ds.vector_sum
+        @item_mean=@ds.vector_mean.mean
+        @mean=@total.mean
+        @median=@total.median
+        @skew=@total.skew
+        @kurtosis=@total.kurtosis
+        @sd = @total.sd
+        @variance=@total.variance
+        @valid_n = @total.size
+        opts_default={:name=>"Reliability Analisis"}
+        @opts=opts_default.merge(opts)
+        @name=@opts[:name]
+        # Mean for covariances and variances
+        @variances=@ds.fields.map {|f| @ds[f].variance}.to_scale
+        @variances_mean=@variances.mean
+        @covariances_mean=(@variance-@variances.sum).quo(@k**2-@k)
+        begin
+          @alpha = Statsample::Reliability.cronbach_alpha(ds)
+          @alpha_standarized = Statsample::Reliability.cronbach_alpha_standarized(ds)
+        rescue => e
+          raise DatasetException.new(@ds,e), "Error calculating alpha"
+        end
+      end
+      # Returns a hash with structure
+      def item_characteristic_curve
+        i=0
+        out={}
+        total={}
+        @ds.each do |row|
+          tot=@total[i]
+          @ds.fields.each do |f|
+            out[f]||= {}
+            total[f]||={}
+            out[f][tot]||= 0
+            total[f][tot]||=0
+            out[f][tot]+= row[f]
+            total[f][tot]+=1
+          end
+          i+=1
+        end
+        total.each do |f,var|
+          var.each do |tot,v|
+            out[f][tot]=out[f][tot].to_f / total[f][tot]
+          end
+        end
+        out
+      end
+      def gnuplot_item_characteristic_curve(directory, base="crd",options={})
+        require 'gnuplot'
+
+        crd=item_characteristic_curve
+        @ds.fields.each  do |f|
+          x=[]
+          y=[]
+          Gnuplot.open do |gp|
+            Gnuplot::Plot.new( gp ) do |plot|
+              crd[f].sort.each do |tot,prop|
+                x.push(tot)
+                y.push((prop*100).to_i.to_f/100)
+              end
+              plot.data << Gnuplot::DataSet.new( [x, y] ) do |ds|
+                ds.with = "linespoints"
+                ds.notitle
+              end
+
+            end
+          end
+        end
+      end
+      def svggraph_item_characteristic_curve(directory, base="icc",options={})
+        require 'statsample/graph/svggraph'
+        crd=ItemCharacteristicCurve.new(@ds)
+        @ds.fields.each do |f|
+          factors=@ds[f].factors.sort
+          options={
+            :height=>500,
+            :width=>800,
+            :key=>true
+          }.update(options)
+          graph = ::SVG::Graph::Plot.new(options)
+          factors.each do |factor|
+            factor=factor.to_s
+            dataset=[]
+            crd.curve_field(f, factor).each do |tot,prop|
+              dataset.push(tot)
+              dataset.push((prop*100).to_i.to_f/100)
+            end
+            graph.add_data({
+              :title=>"#{factor}",
+              :data=>dataset
+            })
+          end
+          File.open(directory+"/"+base+"_#{f}.svg","w") {|fp|
+            fp.puts(graph.burn())
+          }
+        end
+      end
+      def item_total_correlation
+        @ds.fields.inject({}) do |a,v|
+          vector=@ds[v].dup
+          ds2=@ds.dup
+          ds2.delete_vector(v)
+          total=ds2.vector_sum
+          a[v]=Statsample::Bivariate.pearson(vector,total)
+          a
+        end
+      end
+      def item_statistics
+        @ds.fields.inject({}) do |a,v|
+          a[v]={:mean=>@ds[v].mean,:sds=>@ds[v].sds}
+          a
+        end
+      end
+      # Returns a dataset with cases ordered by score
+      # and variables ordered by difficulty
+
+      def item_difficulty_analysis
+        dif={}
+        @ds.fields.each{|f| dif[f]=@ds[f].mean }
+        dif_sort=dif.sort{|a,b| -(a[1]<=>b[1])}
+        scores_sort={}
+        scores=@ds.vector_mean
+        scores.each_index{|i| scores_sort[i]=scores[i] }
+        scores_sort=scores_sort.sort{|a,b| a[1]<=>b[1]}
+        ds_new=Statsample::Dataset.new(['case','score'] + dif_sort.collect{|a,b| a})
+        scores_sort.each do |i,score|
+          row=[i, score]
+          case_row=@ds.case_as_hash(i)
+          dif_sort.each{|variable,dif_value| row.push(case_row[variable]) }
+          ds_new.add_case_array(row)
+        end
+        ds_new.update_valid_data
+        ds_new
+      end
+      def stats_if_deleted
+        @ds.fields.inject({}) do |a,v|
+          ds2=@ds.dup
+          ds2.delete_vector(v)
+          total=ds2.vector_sum
+          a[v]={}
+          a[v][:mean]=total.mean
+          a[v][:sds]=total.sds
+          a[v][:variance_sample]=total.variance_sample
+          a[v][:alpha]=Statsample::Reliability.cronbach_alpha(ds2)
+          a
+        end
+      end
+      def report_building(builder)
+        builder.section(:name=>@name) do |s|
+          s.table(:name=>_("Summary for %s") % @name) do |t|
+          t.row [_("Items"), @ds.fields.size]
+          t.row [_("Sum mean"), @mean]
+          t.row [_("Sum sd"), @sd]
+          t.row [_("Sum variance"), @variance]
+          t.row [_("Sum median"), @median]
+          t.hr
+          t.row [_("Item mean"), @item_mean]
+          t.row [_("Skewness"), "%0.4f" % @skew]
+          t.row [_("Kurtosis"), "%0.4f" % @kurtosis]
+          t.hr
+          t.row [_("Valid n"), @valid_n]
+          t.row [_("Cronbach's alpha"), "%0.4f" % @alpha]
+          t.row [_("Standarized Cronbach's alpha"), "%0.4f" % @alpha_standarized]
+          t.hr
+          t.row [_("Variances mean"),  "%g" % @variances_mean]
+          t.row [_("Covariances mean") , "%g" % @covariances_mean]
+          end
+          s.text _("items for obtain alpha(0.8) : %d" % Statsample::Reliability::n_for_desired_alpha(0.8, @variances_mean,@covariances_mean))
+          s.text _("items for obtain alpha(0.9) : %d" % Statsample::Reliability::n_for_desired_alpha(0.9, @variances_mean,@covariances_mean))          
+          itc=item_total_correlation
+          sid=stats_if_deleted
+          is=item_statistics
+          
+          
+          
+          s.table(:name=>_("Items report for %s") % @name, :header=>["item","mean","sd", "mean if deleted", "var if deleted", "sd if deleted"," item-total correl.", "alpha if deleted"]) do |t|
+            @ds.fields.each do |f|
+              t.row(["#{@ds[f].name}(#{f})", sprintf("%0.5f",is[f][:mean]), sprintf("%0.5f",is[f][:sds]), sprintf("%0.5f",sid[f][:mean]), sprintf("%0.5f",sid[f][:variance_sample]), sprintf("%0.5f",sid[f][:sds]),  sprintf("%0.5f",itc[f]), sprintf("%0.5f",sid[f][:alpha])])
+            end # end each
+          end # table
+        end # section
+      end # def
+    end # class
+  end # module
+end # module